Fimeg/letta-server
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
6,295 Commits 1 Branch 0 Tags
48cc73175b7e579b6a46cbd7e3f90e483bbc1f6a
Commit Graph

69 Commits

Author SHA1 Message Date
Ari Webb
48cc73175b feat: parallel tool calling for openai non streaming [LET-4593] (#5773) 
* first hack

* clean up

* first implementation working

* revert package-lock

* remove openai test

* error throw

* typo

* Update integration_test_send_message_v2.py

* Update integration_test_send_message_v2.py

* refine test

* Only make changes for openai non streaming

* Add tests

---------

Co-authored-by: Ari Webb <ari@letta.com>
Co-authored-by: Matt Zhou <mattzh1314@gmail.com>
 2025-11-13 15:36:14 -08:00
Ari Webb
f3a40a41f5 feat: updated backend to not allow minimal for codex [LET-5883] (#5760) 
* updated backend

* add function in openai_client

* remove values before error

* remove test

---------

Co-authored-by: Ari Webb <ari@letta.com>
 2025-11-13 15:35:34 -08:00
Matthew Zhou
09ba075cfa feat: Modify embedding strategy to first halve the batch size v.s. the batc… [LET-5510] (#5434) 
Modify embedding strategy to first halve the batch size v.s. the batch size
 2025-10-24 15:12:11 -07:00
Matthew Zhou
0543a60538 chore: Restore chunk size for openai embeddings (#5431) 
Restore chunk size
 2025-10-24 15:12:11 -07:00
Ari Webb
624c591820 Ari/let 5486 badrequesterror error code 400 error message requested [LET-5486] (#5422) 
* letta agent v2 throw exception not error

* warning instead of error or exception

* decrease min_chunk_size

---------

Co-authored-by: Ari Webb <ari@letta.com>
 2025-10-24 15:12:11 -07:00
Kevin Lin
08da1a64bb feat: parse reasoning_content from OAI proxies (eg. vLLM / OpenRouter) (#5372) 
* reasonig_content support

* fix

* comment

* fix

* rm comment

---------

Co-authored-by: Charles Packer <packercharles@gmail.com>
 2025-10-24 15:11:31 -07:00
cthomas
a1e771877d feat: add model name patch for openrouter (#5303) 
* feat: add model name patch for openrouter

* add comment
 2025-10-09 15:25:21 -07:00
cthomas
f8dce88ce4 feat: support for models that do not allow None content (#5218) 2025-10-07 17:50:50 -07:00
cthomas
a3545110cf feat: add full responses api support in new agent loop (#5051) 
* feat: add full responses api support in new agent loop

* update matrix in workflow

* relax check for reasoning messages for high effort gpt 5

* fix indent

* one more relax
 2025-10-07 17:50:48 -07:00
Matthew Zhou
df5c997da0 feat: Enable dynamic toggling of tool choice in v3 agent loop for OpenAI [LET-4564] (#5042) 
* Add subsequent flag

* Finish integrating constrained/unconstrained toggling on v3 agent loop

* Update tests to run on v3

* Run lint
 2025-10-07 17:50:47 -07:00
Sarah Wooders
b5de42fefd fix: patch summarizers for integration_test_send_message.py (#4919) 
* fix: integration_test_send_message.py

* patch summarizer

* remove print
 2025-10-07 17:50:46 -07:00
Charles Packer
8da15aaf08 fix(core): patch issue where LLM may generate a 'noop' call [PRO-1340] (#4944) 
fix(core): patch issue where LLM may generate a 'noop' call
 2025-10-07 17:50:46 -07:00
Charles Packer
a4041879a4 feat: add new agent loop (squash rebase of OSS PR) (#4815) 
* feat: squash rebase of OSS PR

* fix: revert changes that weren't on manual rebase

* fix: caught another one

* fix: disable force

* chore: drop print

* fix: just stage-api && just publish-api

* fix: make agent_type consistently an arg in the client

* fix: patch multi-modal support

* chore: put in todo stub

* fix: disable hardcoding for tests

* fix: patch validate agent sync (#4882)

patch validate agent sync

* fix: strip bad merge diff

* fix: revert unrelated diff

* fix: react_v2 naming -> letta_v1 naming

* fix: strip bad merge

---------

Co-authored-by: Kevin Lin <klin5061@gmail.com>
 2025-10-07 17:50:45 -07:00
Charles Packer
9edc7f4d64 feat: add OpenRouterProvider (#4848) 
* feat: init add of openrouter provider, doesn't work bc no key pass and no header pass

* fix: working
 2025-10-07 17:50:45 -07:00
Kian Jones
b8e9a80d93 merge this (#4759) 
* wait I forgot to comit locally

* cp the entire core directory and then rm the .git subdir
 2025-09-17 15:47:40 -07:00
Kian Jones
22f70ca07c chore: officially migrate to submodule (#4502) 
* remove apps/core and apps/fern

* fix precommit

* add submodule updates in workflows

* submodule

* remove core tests

* update core revision

* Add submodules: true to all GitHub workflows

- Ensure all workflows can access git submodules
- Add submodules support to deployment, test, and CI workflows
- Fix YAML syntax issues in workflow files

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* remove core-lint

* upgrade core with latest main of oss

---------

Co-authored-by: Claude <noreply@anthropic.com>
 2025-09-09 12:45:53 -07:00
Matthew Zhou
0eed3722cc feat: Robustify openai embedding [LET-4256] (#4478) 
* Robustify embedding

* Remove unecessary imports

* Add test embeddings
 2025-09-08 17:18:54 -07:00
Charles Packer
1ae0ab1790 fix: properly throw context window exceeded error on the new style of… [LET-4179] (#4380) 
fix: properly throw context window exceeded error on the new style of context window overflow from gpt-5
 2025-09-02 22:20:46 -07:00
Charles Packer
264171f327 fix: patch streaming hidden reasoning event [LET-4167] (#4367) 
* fix: patch streaming hidden reasoning event

* fix: patch reasoning_effort not getting passed to openai
 2025-09-02 16:21:18 -07:00
Charles Packer
a696d9e3d5 fix: various fixes to make gpt-5 work better [LET-4138] (#4344) 
* fix: patch gpt-5 compat

* feat: add verbosity level dropdown selector to llm config panel in ade

* fix: patch duplicated logic

* fix: make default verbosity None, just stage just publish

* fix: missing files
 2025-09-02 10:30:25 -07:00
cthomas
1edcc13778 feat: support filtering out messages when converting to openai dict (#4337) 
* feat: support filtering out messages when converting to openai dict

* fix imports
 2025-09-01 12:48:45 -07:00
Kian Jones
fecf6decfb chore: migrate to ruff (#4305) 
* base requirements

* autofix

* Configure ruff for Python linting and formatting

- Set up minimal ruff configuration with basic checks (E, W, F, I)
- Add temporary ignores for common issues during migration
- Configure pre-commit hooks to use ruff with pass_filenames
- This enables gradual migration from black to ruff

* Delete sdj

* autofixed only

* migrate lint action

* more autofixed

* more fixes

* change precommit

* try changing the hook

* try this stuff
 2025-08-29 11:11:19 -07:00
cthomas
c7b71ad8a9 feat: add new xai llm client (#3936) 2025-08-20 15:49:09 -07:00
Kevin Lin
a22d6b1315 feat: GPT-5 support (#3924) 
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
 2025-08-15 19:01:50 -07:00
cthomas
9f84fb8500 feat: refactor byok logic in llm clients (#3880) 2025-08-12 14:19:02 -07:00
cthomas
2e19f2a801 feat: add new together llm client (#3875) 2025-08-12 13:37:20 -07:00
cthomas
5cf807574f feat: consolidate reasoning model checks (#3862) 2025-08-11 16:55:45 -07:00
Sarah Wooders
b85f8aa43c feat: support opus 4.1 and gpt-5 (#3806) 2025-08-07 15:11:57 -07:00
jnjpng
9d8a122da0 fix: lmstudio support for qwen and llama 
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
Co-authored-by: Charles Packer <packercharles@gmail.com>
 2025-07-29 15:57:20 -07:00
Andy Li
04e9f43220 chore: strings lint cleanup (#3374) 2025-07-18 09:20:45 -07:00
Charles Packer
12c2b49461 fix: add frequency penalty for gpt-4o-mini (#3166) 2025-07-06 11:05:31 -07:00
Matthew Zhou
efca9d8ea0 feat: Only add suffix on duplication (#3120) 2025-07-01 13:48:38 -07:00
Matthew Zhou
5dccccec21 fix: Fix constraints and also implement bulk attach (#3107) 2025-06-30 14:27:57 -07:00
Andy Li
734680db81 feat: timeout configuration for LLM clients + vertex (#2972) 2025-06-23 16:55:23 -07:00
Kevin Lin
65530e8380 fix: add exceptions to accept_developer_role (#2848) 2025-06-16 15:14:40 -07:00
Kevin Lin
93c15244ab feat: add reasoning models to integration_test_send_message (#2710) 2025-06-13 14:54:37 -07:00
cthomas
c1255dc9d1 feat: make tool calls required for model proxy (#2756) 2025-06-11 11:36:45 -07:00
cthomas
5ecd8a706c fix: parallel tool calling OpenAI (#2738) 2025-06-10 14:27:01 -07:00
cthomas
b332ebfa85 feat: support multi content part input (#2717) 2025-06-10 13:36:17 -07:00
Matthew Zhou
b53be62e7a fix: Turn parallel tool calling off for OpenAI (#2737) 2025-06-10 13:27:00 -07:00
cthomas
20e6732f36 feat: add multi-modal input support (#2590) 2025-06-08 18:28:01 -07:00
cthomas
e4da78fce7 fix: gracefully handle too long responses from llm provider (#2677) 2025-06-06 13:13:32 -07:00
Andy Li
d2252f2953 feat: otel metrics and expanded collecting (#2647) 
(passed tests in last run)
 2025-06-05 17:20:14 -07:00
Matthew Zhou
82b3222a52 fix: Make OpenAI context window exceeded error more specific (#2624) 2025-06-04 12:57:51 -07:00
Matthew Zhou
87f4bcad9a feat: Add summarization for more scenarios (#2499) 2025-05-29 11:10:13 -07:00
Sarah Wooders
3354f5fe50 feat: concurrently make embedding request and use async client for OpenAI (#2482) 
Co-authored-by: Matthew Zhou <mattzh1314@gmail.com>
 2025-05-28 11:35:22 -07:00
Sarah Wooders
4cc075f1fc feat: add more trace methods (#2471) 2025-05-27 16:56:30 -07:00
cthomas
e813a65351 feat(asyncify): byok in async loop (#2421) 2025-05-25 19:47:20 -07:00
Shangyin Tan
2199d8fdda fix: do not pass temperature to request if model is oai reasoning model (#2189) 
Co-authored-by: Charles Packer <packercharles@gmail.com>
 2025-05-24 21:34:18 -07:00
cthomas
b554171d41 feat: add tracing to llm clients (#2340) 2025-05-22 13:55:32 -07:00